Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

/pdf/imagenet-large-scale-visual-recognition-challenge-caky5nmmix.pdf

ImageNet Large Scale Visual Recognition Challenge

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections&#x2014;one between each layer and its subsequent layer&#x2014;our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.

/pdf/densely-connected-convolutional-networks-i745msea9d.pdf

Densely Connected Convolutional Networks

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

/pdf/rich-feature-hierarchies-for-accurate-object-detection-and-22fvjlggyg.pdf

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

We consider three hypotheses concerning the primate neocortex which have influenced computational neuroscience in recent years. Is the mind modular in terms of its being profitably described as a collection of relatively independent functional units? Does the regular structure of the cortex imply a single algorithm at work, operating on many different inputs in parallel? Can the cognitive differences between humans and our closest primate relatives be explained in terms of a scalable cortical architecture? We bring to bear diverse sources of evidence to argue that the answers to each of these questions -- with some judicious qualifications -- are in the affirmative. In particular, we argue that while our higher cognitive functions may interact in a complicated fashion, many of the component functions operate through well-defined interfaces and, perhaps more important, are built on a neural substrate that scales easily under the control of a modular genetic architecture. Processing in the primary sensory cortices seem amenable to similar algorithmic principles, and, even for those cases where alternative principles are at play, the regular structure of cortex allows the same or greater advantages as the architecture scales. Similar genetic machinery to that used by nature to scale body plans has apparently been applied to scale cortical computations. The resulting replicated computing units can be used to build larger working memory and support deeper recursions needed to qualitatively improve our abilities to handle language, abstraction and social interaction.

/pdf/three-controversial-hypotheses-concerning-computation-in-the-50wrqv8u0h.pdf

Three controversial hypotheses concerning computation in the primate cortex

State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive as new architectures must be designed and trained for every computational setting. To address this problem we develop a recurrent neural network that successively improves prediction quality with each iteration. Importantly, the RNN may be deployed across a range of computational budgets by merely running the model for a variable number of iterations. We find that this architecture is uniquely suited for efficiently segmenting videos. By exploiting the segmentation of past frames, the RNN can perform video segmentation at similar quality but reduced computational cost compared to state-of-the-art image segmentation methods. When applied to static images in the PASCAL VOC 2012 and Cityscapes segmentation datasets, the RNN traces out a speed-accuracy curve that saturates near the performance of state-of-the-art segmentation methods.

Recurrent Segmentation for Variable Computational Budgets

Predicting the future motion of multiple agents is necessary for planning in dynamic environments. This task is challenging for autonomous driving since agents (e.g., vehicles and pedestrians) and their associated behaviors may be diverse and influence each other. Most prior work has focused on first predicting independent futures for each agent based on all past motion, and then planning against these independent predictions. However, planning against fixed predictions can suffer from the inability to represent the future interaction possibilities between different agents, leading to sub-optimal planning. In this work, we formulate a model for predicting the behavior of all agents jointly in real-world driving environments in a unified manner. Inspired by recent language modeling approaches, we use a masking strategy as the query to our model, enabling one to invoke a single model to predict agent behavior in many ways, such as potentially conditioned on the goal or full future trajectory of the autonomous vehicle or the behavior of other agents in the environment. Our model architecture fuses heterogeneous world state in a unified Transformer architecture by employing attention across road elements, agent interactions and time steps. We evaluate our approach on autonomous driving datasets for behavior prediction, and achieve state-of-the-art performance. Our work demonstrates that formulating the problem of behavior prediction in a unified architecture with a masking strategy may allow us to have a single model that can perform multiple motion prediction and planning related tasks effectively.

Scene Transformer: A unified multi-task model for behavior prediction and planning

A mechanism for automatic quantification of multimedia production quality is presented. A method of embodiments includes assembling data samples from users, the data samples indicating a relative production quality of a set of content items based on a comparison of production quality between content items in the set, extracting content features from each of the content items in the set, and learning, based on the data samples from the plurality of users, a statistical model on the extracted content features, wherein the learned statistical model can predict a production quality of another content item that is not part of the set of content items.

Mechanism for automatic quantification of multimedia production quality

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new domains involves collecting large labeled datasets, but such datasets can be extremely costly to obtain, especially if each new deployment geography requires additional data with expensive 3D bounding box annotations. We demonstrate that pseudo-labeling for 3D object detection is an effective way to exploit less expensive and more widely available unlabeled data, and can lead to performance gains across various architectures, data augmentation strategies, and sizes of the labeled dataset. Overall, we show that better teacher models lead to better student models, and that we can distill expensive teachers into efficient, simple students. 
Specifically, we demonstrate that pseudo-label-trained student models can outperform supervised models trained on 3-10 times the amount of labeled examples. Using PointPillars [24], a two-year-old architecture, as our student model, we are able to achieve state of the art accuracy simply by leveraging large quantities of pseudo-labeled data. Lastly, we show that these student models generalize better than supervised models to a new domain in which we only have unlabeled data, making pseudo-label training an effective form of unsupervised domain adaptation.

Jonathon Shlens

Papers

Three controversial hypotheses concerning computation in the primate cortex

Recurrent Segmentation for Variable Computational Budgets

Scene Transformer: A unified multi-task model for behavior prediction and planning

Mechanism for automatic quantification of multimedia production quality

Pseudo-labeling for Scalable 3D Object Detection.